Latent Visual Reasoning

Follow this topic Ask about this topic

Momentum

8 papers in the last four weeks, against 2 the four weeks before. 0.1% of all new papers.

Jul 13Week of Sep 28

Latest papers 69

All topics

Think Before You Paint: Recursive Latent Reasoning for Diffusion Models
Oct 7, 2026Paweł Skierś, Małgorzata Grzanka, Wojciech Masarczyk +2Latent Visual Reasoning Diffusion Models
Warsaw University of Technology · IDEAS Research Institute · University of Amsterdam
CALR: Continuous Anchored Latent Reasoning via Render-of-Thought Compression
Oct 5, 2026Zhaoyang Wei, Bowen Jiang, Yanchao Hao +5Efficient Language Model Reasoning Latent Visual Reasoning
University of the Chinese Academy of Sciences · Tencent
ReMAP: Restoring the Perceptual Cycle with Reasoning-Time Latent Visual Memory
Oct 4, 2026Hao Jiang, Zhanyu Guo, Chenwei Wu +11Memory-Augmented VLMs Efficient Multimodal Inference
University of Electronic Science and Technology of China · University of Michigan, Ann Arbor · Nanyang Technological University +5
Imagine the Future, Internalize the Gist: Efficient VLA Reasoning via Internalized Spatiotemporal Imagination
Oct 2, 2026Shenglan Li, Zhendong Mi, Hengyi Zhu +6VLMs for Robotics Reasoning for VLA Models
Stevens Institute of Technology · Northeastern University · Arizona State University +1
GeoLatent: Geometry-Guided Latent Structuring with Routed Optimization for 3D Reasoning
Oct 1, 2026Yakun Zhu, Yi Bin, Yujuan Ding +53D Spatial Reasoning Geometric Representation Learning
Tongji University · The Hong Kong Polytechnic University
MoLE: Mixture of Latent Experts for Complementary Visual Reasoning
Oct 1, 2026Yingcheng Liu, Tianyi Jiang, Yujuan Ding +5Large Vision-Language Models Latent Visual Reasoning
Tongji University, China · Hong Kong Polytechnic University, Hong Kong · Alibaba Group, China +1
From Perception to Integration: Revisiting the Internal Dynamics of Reasoning in Vision-Language Models
Sep 28, 2026Rong Yu Xu, Prayag Tiwari, Shaolei ZhangEfficient VLM Inference VLM Interpretability
Shenzhen College of International Education · Halmstad University, Sweden · Renmin University of China
Rethinking Latent Visual Reasoning: Grounding Latent Reasoning in Visual Evidence
Sep 28, 2026Xi Xiao, Tianchen Zhao, Youngeun Kim +10Large Vision-Language Models Latent Visual Reasoning
University of Alabama at Birmingham · Amazon AGI · Work done during an internship at Amazon AGI.
Industrial Anomaly Detection via Defect-Grounded Reasoning in Visual Latent Space
Sep 24, 2026Jaron Yeh, Yen-Wei Chang, Jiang Liu +1Industrial Anomaly Detection Anomaly Localization
National Taiwan University · AMD GenAI
Circuit-MLLM: Topological Logic-Guided Latent-Space Visual Reasoning for Circuit Schematic Understanding
Sep 14, 2026Jinyuan Deng, Yuqi Jiang, Wenjing Huang +3Multimodal Large Language Models Multimodal Reasoning
Zhejiang University, Hangzhou, China
Scaffolding Minds: Optimizing Latent Visual Target Representations for Multimodal Reasoning
Aug 20, 2026Haoqiang Kang, Yinpeng Chen, Luyang Liu +5Visual Spatial Reasoning Multimodal Reasoning
Google DeepMind · UC San Diego · Work done at Google DeepMind
Localize, Then Reason: Visual Latent Structural Reasoning for Molecular Properties and Edits
Aug 13, 2026Xingqiao Lin, Junmei Wang, Haocheng TangLatent Visual Reasoning Structured Reasoning
Department of Chemical Engineering, Carnegie Mellon University, Pittsburgh, Pennsylvania 15213, United States · Department of Pharmaceutical Sciences and Computational Chemical Genomics Screening Center, School of Pharmacy, University of Pittsburgh, Pittsburgh, PA, USA · Khoury College of Computer Science, Northeastern University, Boston, MA, USA
ChronoVision: Temporal Reasoning via Latent State Reconstruction
Aug 6, 2026Yifan Shen, Jian Xu, Boyi Li +6Multimodal Large Language Models Latent Visual Reasoning
University of Illinois Urbana-Champaign · PediaMed AI · University of Pennsylvania
LAVE: Latent Visual Evidence-Enhanced Planning for Video Tool-use Agents
Aug 5, 2026Zijian Wang, Junnan Zhu, Rongzhen Li +7Latent Visual Reasoning Tool-Using Vision-Language Agents
College of Computer Science, Chongqing University, Chongqing, China · MAIS, Institute of Automation, Chinese Academy of Sciences · Chongqing National Data AI Research Institute, AI Research Lab +1
Perception Before Reasoning: Dynamic Latent Reasoning for Video Understanding and Question Answering
Aug 4, 2026Haotian Xia, Zilin Xiao, Junbo Zou +2Video QA Latent Visual Reasoning
Department of Computer Science, Rice University · College of Sciences, Georgia Institute of Technology
LiLa-WAM: Lightweight Latent Reasoning World-Action Model for Robotic Manipulation
Aug 4, 2026Fan Yang, Yuting Su, Xiaobo Wang +7World Models for Robotics Latent Visual Reasoning
1Tianjin University · 2Shenzhen University of Advanced Technology · 5Sangfor Technologies Inc. +2
Balancing Efficiency and Efficacy: Training-Free Attention-Guided Switching Between Explicit and Latent Thoughts for MLLMs
Aug 4, 2026Haoqian Kang, Liupeng Li, Kuofeng Gao +5Efficient Multimodal Inference Multimodal Large Language Models
Harbin Institute of Technology, Shenzhen Shenzhen, China · Tsinghua Shenzhen International Graduate School, Tsinghua University Shenzhen, China · Peng Cheng Laboratory Shenzhen, China +1
LUT: Latent Utility Training for Visual Reasoning
Aug 1, 2026Jiaxuan Kang, Siyu Chen, Mingda Li +6Visual Question Answering Large Vision-Language Models
Tencent PCG
OPLD: On-Policy Latent Distillation for Multimodal Reasoning
Jul 30, 2026Shoutai Zhu, Tianyang Xu, Bin Sun +3Multimodal Reasoning Latent Visual Reasoning
ByteDance
GeoAnchor: Collaborative Reasoning via Latent Decomposition for 3D Spatial Understanding
Jul 15, 2026Hao Li, Han Fang, Zixin Pan +83D Spatial Reasoning Latent Visual Reasoning
Shanghai Jiao Tong University · Xingchen AGI Lab, China Telecom Artificial Intelligence Technology (Beijing) · The Hong Kong University of Science and Technology (Guangzhou) +1
Playing ZendoWorld: Challenging AI Agents on Active Visual Concept Induction
Jul 9, 2026Sophia Koehler, Antonia Wüst, Inga Ibs +5AI Agent Evaluation Active Learning
1AIML Lab, TU Darmstadt · 2Hessian Center for AI (hessian.AI) · Psychology of Information Processing, TU Darmstadt +4
MentalThink: Shaping Thoughts in Mental SVG World
Jul 3, 2026Kangheng Lin, Jisheng Yin, Dingming Li +11Visual Spatial Reasoning Latent Visual Reasoning
State Key Laboratory of Networking and Switching Technology, Beijing University of Posts and Telecommunications · University of Chinese Academy of Sciences · StepFun
ProLaViT: Learning Progressive Latent Visual Thoughts in Structured Latent Space
Jul 3, 2026Peiming Li, Yifan Wang, Xiaotian Zhang +4Multimodal Large Language Models Latent Visual Reasoning
Basic Algorithm Center, PCG, Tencent · Zhejiang University · Peking University
Multimodal Continuous Reasoning via Asymmetric Mutual Variational Learning
Jul 1, 2026Shijie Li, Yilin Gao, Siyuan Yang +7Multimodal Large Language Models Latent Visual Reasoning
Shanghai Jiao Tong University · Ant Group
CoLT: Teaching Multi-Modal Models to Think with Chain of Latent Thoughts
Jun 30, 2026Lianyu Hu, Shengqian Qin, Zeqin Liao +4Efficient Multimodal Inference Efficient Language Model Reasoning
Nanyang Technological University, Singapore · Shanghai Jiao Tong University, China · NKIARI, Shenzhen Futian, China +2
Decodable Is Not Grounded: A Vision-Ablation Arbiter for VLM Spatial Reasoning
Jun 30, 2026Chih-Ting Liao, Fei Shen, Xin Cao +1Visual Spatial Reasoning VLM Interpretability
University of New South Wales · National University of Singapore
Latent Visual Diffusion Reasoning with Monte Carlo Tree Search
Jun 26, 2026Xirui Teng, Nan Xi, Junsong YuanLatent Visual Reasoning Visually Grounded Reasoning
Beijing Jiaotong University, Beijing, China · Virginia Commonwealth University, Richmond VA, USA · University at Buffalo, Buffalo NY, USA
From Hallucination to Grounding: Diagnosing Visual Spatial Intelligence via CRISP
Jun 25, 2026Zhixing Li, Yinan YuVLM Evaluation Spatial Reasoning Benchmarks
Chalmers University of Technology, Gothenburg, Sweden
IV-CoT: Implicit Visual Chain-of-Thought for Structure-Aware Text-to-Image Generation
Jun 23, 2026Zixuan Li, Haokun Lin, Yicheng Xiao +10T2I Generation Multimodal Large Language Models
NLPR, Institute of Automation, Chinese Academy of Sciences · The University of Hong Kong · Ant Group
Latent Visual States for Efficient Multimodal Reasoning
Jun 23, 2026Xiuwei Chen, Wentao Hu, Yongxin Wang +8Efficient Multimodal Inference Large Vision-Language Models
Sun Yat-sen University · The Hong Kong Polytechnic University · MBZUAI +2

Oct 7, 2026, cs.AIJ/K move · Enter open · S save

Think Before You Paint: Recursive Latent Reasoning for Diffusion Models

Paweł Skierś, Małgorzata Grzanka, Wojciech Masarczyk, Jan-Willem van de Meent+1

Warsaw University of Technology · IDEAS Research Institute · University of Amsterdam

Latent Visual Reasoning Diffusion Models Constrained Generative Modeling Pixel-Space Diffusion Models

Open paper AskPDF arXiv

Diffusion models generate realistic images but often fail on visual reasoning tasks, such as filling in a Sudoku or drawing the path through a maze. When a discrete symbolic representation is available, recursive methods such as the Tiny Recursive Model (TRM) solve even hard instances of these puzzles. We ask how such reasoning can be carried over to pixels, where no symbolic representation is available. We propose Painter-Thinker (PaTh): a small recursive network (the Thinker) reasons over a grid of learned tokens that encode the noisy image and the conditioning, refines a latent state within every denoising step, and steers a frozen diffusion model (the Painter) through ControlNet adapters. The Thinker is trained with the standard reconstruction loss alone, without symbolic targets, a solver, or a verifier. PaTh solves 92.5% of hard MNIST Sudoku puzzles (prior best 75%) and 71.2% of extreme ones (prior best 4.1%), with 10M parameters against 82M for a standard diffusion model. It also improves on mazes, Queens, and CLEVR scenes with specified spatial relations, and its advantage grows with problem size. Diagnostic experiments show that PaTh recovers from injected mistakes that the diffusion model cannot repair, especially when many cells are wrong. Together, these results show that reasoning mechanisms developed for symbolic data can be integrated into pixel-space diffusion without symbolic supervision, opening a path toward generating data under increasingly complex constraints.

Momentum

Related topics

Latest papers 69